© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10216
    Prev
    Next
    INDEX
    Explanations

    water and power

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.81
    AndEndTag
    -0.76
     незавершена
    -0.75
     للمعارف
    -0.72
    archiviato
    -0.69
     AttributeSet
    -0.68
    bootstrapcdn
    -0.68
    gwt
    -0.67
    ⓘ
    -0.64
    Vidite
    -0.63
    POSITIVE LOGITS
    ue
    0.46
    bara
    0.44
    ExtendWith
    0.43
    ünd
    0.42
    endar
    0.41
    ktı
    0.40
     AssemblyTitle
    0.40
     Works
    0.40
    UE
    0.40
    éndole
    0.39
    Activations Density 0.003%

    No Known Activations